David Burton
I build systems that learn from data.
From algorithmic trading to Alzheimer's research — wherever data has weight, I build the system.
// projects
Atlas Trading System
ML ensemble manages real capital in live markets. Event-driven trading system with machine learning ensemble models that predict market movement and execute trades autonomously. Trained on 2.48 million data points with walk-forward validation.
Cognitive Health Study
130K longitudinal observations, one question about aging. Large-scale biostatistics study investigating medication effects on cognitive decline in 30,000+ older adults. Uses survival analysis and propensity score matching. Under peer review.
Lead Generation Engine
Automated intelligence pipeline behind a $30M sales year.
Grant Writing Agent
NLP system that reverse-engineers winning proposals.
Email Automation Platform
Behavior-driven email engine sending 100K messages per hour.
Adaptive Learning Engine
Real-time ML adapts difficulty as learners progress.
Quantitative Developer
Atlas Trading System
Built and operate a production algorithmic trading system on SPY options managing real capital. ML ensemble models, 2.48M training data points, sub-millisecond feature calculation. Primary income source.
Independent Research & Consulting
NYC
Alzheimer's research with the University of Kansas neurology department using the NACC dataset — 130K+ observations, under peer review. Computational biology platform for an RNA interference biotech startup. Agentic AI systems.
Data Scientist
BTL Industries
Built the lead generation platform that helped the sales team win President's Club — $30M revenue, 2x the next team. Automated lead scraping, NLP validation, enterprise client workshops.
Data Analyst
Prenda · Freelance
Student tracking dashboards for 10K+ students. Grant writing automation (40% efficiency gain, 200% funding increase). Predictive models for nonprofit donor behavior.
Mathematics Teacher
International schools
Taught mathematics internationally before retraining into data science. Purdue BA, Indiana M.S. Ed. The teaching background is why I explain things the way I do.
Building Atlas: Production ML at Scale
Deploying a forecasting system with real capital on the line — model selection, monitoring, and what breaks in production.
[Case Study]Replacing DuckDB: 10x with Rust
Building a custom time-series query engine with predicate pushdown that outperformed DuckDB by an order of magnitude.
[Reference]ML Deployment: Prototype to Production
The gap between a working notebook and a production system — monitoring, versioning, and the infrastructure nobody talks about.
[Tutorial]Data Viz with WebAssembly & Rust
Interactive visualizations compiled to WASM — near-native performance in the browser for datasets that would choke JavaScript.
You made it to the end. That usually means something here was relevant to what you're building.
Send a message
If it's about data, trading systems, research, or something I haven't thought of yet — I'd like to hear about it.
Elsewhere
New York City —